This item is non-discoverable
Loading...
Non-discoverable
FFDNet: Toward a fast and flexible solution for CNN-Based image denoising
Zhang, K Zuo, W Zhang, L
Zhang, K
Zuo, W
Zhang, L
Citations
Altmetric:
Genre
Pre-print
Date
2018-09-01
Advisor
Committee member
Group
Department
Permanent link to this record
Collections
Research Projects
Organizational Units
Journal Issue
DOI
10.1109/TIP.2018.2839891
Abstract
© 1992-2012 IEEE. Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising. However, these methods mostly learn a specific model for each noise level, and require multiple models for denoising images with different noise levels. They also lack flexibility to deal with spatially variant noise, limiting their applications in practical denoising. To address these issues, we present a fast and flexible denoising convolutional neural network, namely FFDNet, with a tunable noise level map as the input. The proposed FFDNet works on downsampled sub-images, achieving a good trade-off between inference speed and denoising performance. In contrast to the existing discriminative denoisers, FFDNet enjoys several desirable properties, including: 1) the ability to handle a wide range of noise levels (i.e., [0, 75]) effectively with a single network; 2) the ability to remove spatially variant noise by specifying a non-uniform noise level map; and 3) faster speed than benchmark BM3D even on CPU without sacrificing denoising performance. Extensive experiments on synthetic and real noisy images are conducted to evaluate FFDNet in comparison with state-of-the-art denoisers. The results show that FFDNet is effective and efficient, making it highly attractive for practical denoising applications.
Description
Citation
Citation to related work
Institute of Electrical and Electronics Engineers (IEEE)
Has part
IEEE Transactions on Image Processing
ADA compliance
For Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact scholarshare@temple.edu